© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 61682
    Prev
    Next
    INDEX
    Explanations

    Requirements, possessions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hometown
    -0.07
    Ymd
    -0.07
     hr
    -0.07
    Sad
    -0.07
    这个
    -0.07
     Captain
    -0.07
    	count
    -0.06
     Cow
    -0.06
    атом
    -0.06
    Poor
    -0.06
    POSITIVE LOGITS
    ическим
    0.07
     deactivated
    0.07
     臺
    0.06
    -fashioned
    0.06
    執
    0.06
     almaktadır
    0.06
     продовж
    0.06
    ीं।
    0.06
     vypad
    0.06
    ':['
    0.06
    Activations Density 0.024%

    No Known Activations